Triple
T10880478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway 4R (Newark) |
E256905
|
entity |
| Predicate | hasOppositeRunwayNumber |
P66860
|
FINISHED |
| Object | 22L |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 22L | Statement: [Runway 4R (Newark), hasOppositeRunwayNumber, 22L]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOppositeRunwayNumber Context triple: [Runway 4R (Newark), hasOppositeRunwayNumber, 22L]
-
A.
hasOppositeRunway
chosen
Indicates that one runway is paired with another runway that has the opposite or reciprocal orientation or designation.
-
B.
hasParallelRunwayIndicator
Indicates that one runway serves as a parallel counterpart or reference indicator for another runway within an airport or airfield.
-
C.
hasRunwayDesignationSide
Indicates that a runway designation is associated with a specific side or direction of the runway (e.g., left, right, or center).
-
D.
hasParallelRunway
Indicates that one runway is parallel in orientation and alignment to another runway.
-
E.
hasRunwayOrientation
Indicates that a runway is aligned or oriented in a specific directional heading.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d6aa848804819081b2713ca0bedf06 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d751b031a88190b1182dfc1f520264 |
completed | April 9, 2026, 7:13 a.m. |
| PD | Predicate disambiguation | batch_69d70d360c388190a3d829fe8862434f |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:21 p.m.